Coding
Like-for-like- Hy4 preview
- 65.7
- Step 3.7 Flash
- 56.3
- Weighted basis
- 1 vs 1 rows
- Reading
- Hy4 preview leads
Hy4 preview vs Step 3.7 Flash
Updated August 28, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.
Decision reading
Hy4 preview has the higher public score, 79.16 versus 51.05, and the 90% score intervals do not overlap.
2 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Coding work
Code generation, repair, and software-engineering tasks
Hy4 preview
Hy4 preview leads on the same 1 weighted benchmark row.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Hy4 preview
Hy4 preview has the larger documented context window.
Confidence: documented
Show secondary and unsupported calls
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
No shared weighted benchmark basis supports a winner.
Confidence: limited
Chat turn cost
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: rate-fallback
Repository review cost
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Confidence: listed-rates
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
26 Hy4 preview only
2 Shared
9 Step 3.7 Flash only
- Shared results
- 2
- Hy4 preview only
- 26
- Step 3.7 Flash only
- 9
- Like-for-like categories
- 1 / 8
Category results, on a stated basis
Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.
Agentic
Not comparable- Hy4 preview
- Not measured
- Step 3.7 Flash
- 66.4
- Weighted basis
- 0 vs 2 rows
- Reading
- Not comparable
Reasoning
Not comparable- Hy4 preview
- Not measured
- Step 3.7 Flash
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Knowledge
Not comparable- Hy4 preview
- 60.4
- Step 3.7 Flash
- Not measured
- Weighted basis
- 2 vs 0 rows
- Reading
- Not comparable
Math
Not comparable- Hy4 preview
- Not measured
- Step 3.7 Flash
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multilingual
Not comparable- Hy4 preview
- Not measured
- Step 3.7 Flash
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
Multimodal
Not comparable- Hy4 preview
- 66.2
- Step 3.7 Flash
- Not measured
- Weighted basis
- 1 vs 0 rows
- Reading
- Not comparable
Instruction following
Not comparable- Hy4 preview
- Not measured
- Step 3.7 Flash
- Not measured
- Weighted basis
- 0 vs 0 rows
- Reading
- Not comparable
| Category | Hy4 preview | Step 3.7 Flash | Weighted basis | Reading |
|---|---|---|---|---|
| Coding | 65.7 | 56.3 | Like-for-like1 vs 1 rows | Hy4 preview leads |
| Agentic | Not measured | 66.4 | Not comparable0 vs 2 rows | Not comparable |
| Reasoning | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Knowledge | 60.4 | Not measured | Not comparable2 vs 0 rows | Not comparable |
| Math | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multilingual | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
| Multimodal | 66.2 | Not measured | Not comparable1 vs 0 rows | Not comparable |
| Instruction following | Not measured | Not measured | Not comparable0 vs 0 rows | Not comparable |
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
SWE-bench Pro
Coding
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- Hy4 preview
- Self-hosted; infrastructure cost varies
- Fits in one request
- Step 3.7 Flash
- $0.00077
- Fits in one request
Hy4 preview has no comparable published API token rate.
Repository review
50K fresh input + 3K output tokens
- Hy4 preview
- Self-hosted; infrastructure cost varies
- Fits in one request
- Step 3.7 Flash
- $0.01345
- Fits in one request
Hy4 preview has no comparable published API token rate.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- Hy4 preview
- Self-hosted; infrastructure cost varies
- Fits in one request
- Cached-input rate unavailable
- Step 3.7 Flash
- $0.0555
- Fits in one request
- Cached input priced at the published list-input rate
Step 3.7 Flash has no published cached-input rate, so cached tokens use its listed input rate. Hy4 preview has no comparable published API token rate.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationHy4 previewStep 3.7 Flash
Context window
Maximum documented context; output-token limits may be lower.
Hy4 preview
Step 3.7 Flash
256K
API model ID
Hy4 preview
tencent/Hy4-preview
Tencent Hy4 preview model cardStep 3.7 Flash
Not sourced
Cached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Hy4 preview
No comparable hosted API rate
Tencent Hy4 preview model cardStep 3.7 Flash
Not published
Documented inputs
Hy4 preview
Not sourced
Step 3.7 Flash
Not sourced
Documented outputs
Hy4 preview
Not sourced
Step 3.7 Flash
Not sourced
Provider availability
Hy4 preview
Not sourced
Step 3.7 Flash
Not sourced
Reasoning profile
Hy4 preview
Reasoning
Step 3.7 Flash
Reasoning
Weight access
Hy4 preview
Open Weight
Step 3.7 Flash
Open Weight
License
Hy4 preview
Open Weight
Step 3.7 Flash
Open Weight
Release date
Hy4 preview
2026-08-28
Step 3.7 Flash
2026-05-29
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Hy4 preview has the higher public score, 79.16 versus 51.05, and the 90% score intervals do not overlap.
- Workload cost
- A complete comparable API-rate estimate is not available for both models.
- Context tradeoff
- Hy4 preview has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence37 rows
Agentic
Terminal-Bench 2.1
Hy4 preview85.4%SourceStep 3.7 Flash—Not directly comparable
CyberGym
Hy4 preview78.4%SourceStep 3.7 Flash—Not directly comparable
WideResearch
Hy4 preview83.9%SourceStep 3.7 Flash—Not directly comparable
DRACO
Hy4 preview77.2%SourceStep 3.7 Flash—Not directly comparable
MCP Atlas
Hy4 preview83.7%SourceStep 3.7 Flash—Not directly comparable
Toolathlon-Verified
Hy4 preview74.1%SourceStep 3.7 Flash—Not directly comparable
APEX-Agents
Hy4 preview37.1%SourceStep 3.7 Flash—Not directly comparable
skillsBench
Hy4 preview62.9%SourceStep 3.7 Flash—Not directly comparable
JobBench
Hy4 preview61.7%SourceStep 3.7 Flash—Not directly comparable
Agents' Last Exam
Hy4 preview22.8%SourceStep 3.7 Flash—Not directly comparable
AutomationBench
Hy4 preview32.1%SourceStep 3.7 Flash—Not directly comparable
BankerToolBench
Hy4 preview78.6%SourceStep 3.7 Flash—Not directly comparable
HLE w/ tools
Hy4 preview55.4%SourceStep 3.7 Flash47.2%SourceHy4 preview leads this result
Terminal-Bench 2.0
Hy4 preview—Step 3.7 Flash59.5%SourceNot directly comparable
BrowseComp
Hy4 preview—Step 3.7 Flash75.8%SourceNot directly comparable
DeepSearchQA
Hy4 preview—Step 3.7 Flash92.8%SourceNot directly comparable
Toolathlon
Hy4 preview—Step 3.7 Flash49.5%SourceNot directly comparable
Claw-Eval
Hy4 preview—Step 3.7 Flash67.1%SourceNot directly comparable
Gert Labs
Hy4 preview—Step 3.7 Flash51.57%SourceNot directly comparable
Coding
Terminal-Bench 2.1
Hy4 preview85.4%SourceStep 3.7 Flash—Not directly comparable
SWE-bench Pro
Hy4 preview65.7%SourceStep 3.7 Flash56.3%SourceHy4 preview leads this result
SWE Multilingual
Hy4 preview82.9%SourceStep 3.7 Flash—Not directly comparable
deepSwe
Hy4 preview64.3%SourceStep 3.7 Flash—Not directly comparable
NL2Repo
Hy4 preview58.9%SourceStep 3.7 Flash—Not directly comparable
ProgramBench
Hy4 preview17.5%SourceStep 3.7 Flash—Not directly comparable
PostTrain Bench
Hy4 preview35.6%SourceStep 3.7 Flash—Not directly comparable
sweMarathon
Hy4 preview31.9%SourceStep 3.7 Flash—Not directly comparable
Terminal-Bench 2.0
Hy4 preview—Step 3.7 Flash59.5%SourceNot directly comparable
Reasoning
CritPt
Hy4 preview16.9%SourceStep 3.7 Flash—Not directly comparable
Knowledge
Math
Apex
Hy4 preview74.2%SourceStep 3.7 Flash—Not directly comparable
Multimodal
Frequently asked questions
Which is better, Hy4 preview or Step 3.7 Flash?
Hy4 preview has the higher public score, 79.16 versus 51.05, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
Which is better for coding, Hy4 preview or Step 3.7 Flash?
Hy4 preview leads the like-for-like coding comparison across 1 shared weighted benchmark row.
Which is better for agentic tasks, Hy4 preview or Step 3.7 Flash?
The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.
Which costs less, Hy4 preview or Step 3.7 Flash?
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Which has the larger context window, Hy4 preview or Step 3.7 Flash?
Hy4 preview has the larger documented context window: 1M, compared with 256K.
Related comparisons
Last updated August 28, 2026
Watch Hy4 preview vs Step 3.7 Flash
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.